Search

This study presents the implementation and evaluation of a convolutional neural network (CNN) based image segmentation model using the U-Net architecture for forest image segmentation. The proposed algorithm starts by preprocessing the datasets of satellite images and corresponding masks from a repository source. Data preprocessing involves resizing, normalizing, and splitting the images and masks into training and testing datasets. The U-Net model architecture, comprising encoder and decoder parts with skip connections, is defined and compiled with binary cross-entropy loss and Adam optimizer. Training includes early stopping and checkpoint saving mechanisms to prevent overfitting and retain the best model weights. Evaluation metrics such as Intersection over Union (IoU), Dice coefficient, pixel accuracy, precision, recall, specificity, and F1-score are computed to assess the model's performance. Visualization of results includes comparing predicted segmentation masks with ground truth masks for qualitative analysis. The study emphasizes the importance of training data size in achieving accurate segmentation models and highlights the potential of U-Net architecture for forest image segmentation tasks.

Postoperative tumor recurrence remains a predominant cause of treatment failure. In this study, we developed an in situinjectable hydrogel, termed MPB-NO@DOX + ATRA gel, which was locally formed within the tumor resection cavity. The MPB-NO@DOX + ATRA gel was fabricated by mixing a thrombin solution, a fibrinogen solution containing all-trans retinoic acid (ATRA), and a Mn/NO-based immune nano-activator termed MPB-NO@DOX. ATRA promoted the differentiation of cancer stem cells, inhibited cancer cell migration, and affected the polarization of tumor-associated macrophages. The outer MnO2shell disintegrated due to its reaction with glutathione and hydrogen peroxide in the cytoplasm to release Mn2+and produce O2, resulting in the release of doxorubicin (DOX). The released DOX entered the nucleus and destroyed DNA, and the fragmented DNA cooperated with Mn2+to activate the cGAS-STING pathway and stimulate an anti-tumor immune response. In addition, when MPB-NO@DOX was exposed to 808 nm laser irradiation, the Fe-NO bond was broken to release NO, which downregulated the expression of PD-L1 on the surface of tumor cells and reversed the immunosuppressive tumor microenvironment. In conclusion, the MPB-NO@DOX + ATRA gel exhibited excellent anti-tumor efficacy. The results of this study demonstrated the great potential of in situinjectable hydrogels in preventing postoperative tumor recurrence.

Multidrug resistance (MDR) remains a formidable challenge to effective clinical cancer therapy. Herein, a nonviral gene delivery system HA/anti-miR-21/PPAuNCs to overcome MDR was reported. This system could condense the microRNA-21 inhibitor (anti-miR-21) into hyaluronic acid-conjugated and polyethylenimine-modified PEGylated gold nanocages (AuNCs) and had good stability. In vitro studies demonstrated that HA/anti-miR-21/PPAuNCs could enhance intracellular DOX accumulation in DOX-resistant HCC cells (HepG2/ADR cells) and increase the sensitivity to DOX of HepG2/ADR cells through upregulating PTEN protein expression mediated by anti-miR-21 and downregulating P-gp protein expression mediated by the hyperthermia of HA/PPAuNCs upon mild near-infrared irradiation. Furthermore, the therapeutic effects had been enhanced due to the combination of chemotherapy, gene therapy, and photothermal therapy. Besides, HA/anti-miR-21/PPAuNCs have a good biocompatibility. These findings can provide new insights and strategies for the treatment of cancers with MDR.

Glucose-responsive insulin delivery systems, which can maintain a stable level of blood glucose, have been proposed as a promising method to treat diabetes. Such systems can reduce potential toxicity and enhance patient compliance compared to traditional therapies. Accordingly, we designed a mesoporous silica nanoparticle (MSN)-based glucose-sensitive and self-regulated drug release system to achieve the goal of long circulation and “touch switch” in vivo. In this system, carboxyphenylboronic acid (CPBA) was first modified on the surface of MSN using amidation reaction. Insulin (INS) was then loaded in the channels of MSN (CPBA-MSN/INS) through physical adsorption, and sodium alginate (SA) was introduced onto the surface of the CPBA-MSN/INS nanoparticles as the gatekeeper via amidation reaction (SA/CPBA-MSN/INS). We found the drug loading capacity of INS was 261 mg/g. In the normal range of blood glucose, INS was scarcely released due to the reversible covalent interaction between 1,2-diols of SA and CPBA. Within the high concentration of glucose, the boronate esters could be dissociated, which results in the mesoporous channels opening and the release of INS. In vivo experiments on diabetic mice showed SA/CPBA-MSN/INS sustained a normal blood glucose level for up to 12 h with a single dose. Moreover, the lipid metabolism disorder and organ damage of diabetic mice were alleviated after treatment with SA/CPBA-MSN/INS. Therefore, SA/CPBA-MSN/INS characterized by an “on–off” regulated drug release property and high biosafety shows promise for applications in diabetes treatment.